A method and system for modular assembly control of a wall panel of a ship cabin

Abstract

The embodiment of the application provides a ship cabin wallboard modular assembly control method and system, comprising: acquiring length data and width data of a wallboard; calculating first initial current of a first magnetic field excitation array and second initial current of a second magnetic field excitation array according to the length data and the width data; collecting a dielectric loss factor and a vibration frequency coefficient of a wallboard material; controlling operation of the first magnetic field excitation array and the second magnetic field excitation array according to the first operating current and the second operating current and a speed adjustment parameter, inputting the corrected operating current and the speed adjustment parameter into the magnetic field excitation array, realizing accurate control of a high-frequency alternating magnetic field, driving a controllable high-frequency friction heat and self-alignment movement of a wallboard interface, completing modular assembly, and solving the problem of uneven temperature distribution in a traditional heating mode by using the uniform temperature field characteristic of magnetostrictive high-frequency friction heat.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method for controlling the modular assembly of ship cabin wall panels, a control system for the modular assembly of ship cabin wall panels, a computer device, and a storage medium. Background Technology

[0002] Modular assembly of ship cabin panels is a core technology in the construction of modern ships, especially luxury cruise ships and ro-ro passenger ships. This technology has shifted the finishing work, which was traditionally done inside the hull, to a workshop on land.

[0003] Modular assembly typically refers to assembling the cabin's wall panels, ceiling, toilet, furniture, and even piping into an independent, standard box module in a workshop, and then hoisting the whole module into the hull and securing it. While the wall panel modules are assembled independently on land, the enormous lifting force and the inertial forces generated by the ship's movement during the overall hoisting process can cause deformation of the module frame. Improper design of the connection between the wall panels and the frame can easily lead to problems such as door frame deformation and wall panel cracking. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention are proposed to provide a modular assembly control method for ship cabin wall panels, a modular assembly control system for ship cabin wall panels, a computer device, and a storage medium to overcome or at least partially solve the above problems.

[0005] To address the aforementioned problems, this invention discloses a modular assembly control method for ship cabin wall panels, wherein the wall panels include vertical edge channels and horizontal edge channels; a vibration connection device operates within the vertical edge channels and horizontal edge channels; the vibration connection device includes a first magnetic field excitation array and a second magnetic field excitation array; the method includes: Obtain the length and width data of the wall panel; The first initial current of the first magnetic field excitation array and the second initial current of the second magnetic field excitation array are calculated based on the length and width data. Collect the dielectric loss factor and vibration frequency coefficient of the wall panel material; The first initial current and the second initial current are corrected according to the dielectric loss factor and the vibration frequency coefficient to obtain the first operating current and the second operating current. The swing distance data of the first magnetic field excitation array and the second magnetic field excitation array are calculated based on the vibration frequency coefficient. Based on the swing distance data, velocity adjustment parameters for the first and second magnetic field excitation arrays are generated; The operation of the first magnetic field excitation array and the second magnetic field excitation array is controlled according to the first operating current, the second operating current, and the speed adjustment parameters.

[0006] This invention discloses a modular assembly control system for ship cabin wall panels, wherein the wall panels include vertical edge channels and horizontal edge channels; a vibration connection device operates within the vertical edge channels and horizontal edge channels; the vibration connection device includes a first magnetic field excitation array and a second magnetic field excitation array; the system includes: The first acquisition module is used to acquire the length and width data of the wall panel; An initial current calculation module is used to calculate the first initial current of the first magnetic field excitation array and the second initial current of the second magnetic field excitation array based on the length data and width data. The acquisition module is used to collect the dielectric loss factor and vibration frequency coefficient of the wall panel material; The current correction module is used to correct the first initial current and the second initial current according to the dielectric loss factor and the vibration frequency coefficient to obtain the first operating current and the second operating current. The swing distance calculation module is used to calculate the swing distance data of the first magnetic field excitation array and the second magnetic field excitation array based on the vibration frequency coefficient. The speed adjustment parameter generation module is used to generate speed adjustment parameters for the first magnetic field excitation array and the second magnetic field excitation array based on the swing distance data. The operation control module is used to control the operation of the first magnetic field excitation array and the second magnetic field excitation array according to the first operating current, the second operating current, and the speed adjustment parameters.

[0007] This invention also discloses a computer device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described steps for modular assembly control of ship cabin wall panels.

[0008] This invention also discloses a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described steps for modular assembly control of ship cabin wall panels.

[0009] The embodiments of the present invention have the following advantages: In this embodiment of the invention, the modular assembly control method for the wall panels of a ship's cabin includes: acquiring length and width data of the wall panels; calculating a first initial current of a first magnetic field excitation array and a second initial current of a second magnetic field excitation array based on the length and width data; collecting the dielectric loss factor and vibration frequency coefficient of the wall panel material; correcting the first and second initial currents based on the dielectric loss factor and vibration frequency coefficient to obtain a first operating current and a second operating current; calculating the swing distance data of the first and second magnetic field excitation arrays based on the vibration frequency coefficient; generating speed adjustment parameters for the first and second magnetic field excitation arrays based on the swing distance data; controlling the operation of the first and second magnetic field excitation arrays based on the first and second operating currents and the speed adjustment parameters, wherein the magnetostrictive material generates high-frequency stretching vibration under the action of a high-frequency magnetic field, driving the wall panel interface to generate relative displacement according to the motion curve set by the speed adjustment parameters, and achieving interface connection through high-frequency frictional heating. By inputting the corrected operating current and speed adjustment parameters into the magnetic field excitation array, precise control of the high-frequency alternating magnetic field is achieved, thereby driving the wall panel interface to generate controllable high-frequency frictional heating and self-aligning motion, completing the modular assembly. Through precise current and speed control, the coordinated control of high-frequency frictional heating and self-aligned motion is achieved; by utilizing the uniform temperature field characteristics of magnetostrictive high-frequency frictional heating, the problem of uneven temperature distribution in traditional heating methods is solved. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a flowchart illustrating the steps of an embodiment of a modular assembly control method for ship cabin wall panels according to an invention. Figure 2 This is a schematic diagram of a wall panel connection according to an embodiment of the present invention; Figure 3 This is a structural block diagram of an embodiment of a modular assembly control system for ship cabin walls according to an embodiment of the present invention; Figure 4 This is an internal structural diagram of a computer device according to one embodiment. Detailed Implementation

[0012] To make the technical problems, technical solutions, and beneficial effects solved by the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the present invention and are not intended to limit the present invention.

[0013] In this embodiment of the invention, magnetostrictive high-frequency triboelectric heating technology is applied to the interface connection of ship hull panels. The dielectric loss factor and vibration frequency coefficient of the hull panel material are used as dual correction parameters. Combined with nonlinear mapping operations (including cross-coupling terms), the initial current is dynamically corrected, and real-time temperature closed-loop compensation is introduced. This concept solves the problem of thermal efficiency fluctuations caused by differences in the parameters of hull panel materials from different batches, improves the uniformity of the temperature field at the connection interface, and achieves quantitative determination of the relative displacement amplitude during the self-alignment stage by querying the swing distance mapping table through the vibration frequency coefficient and combining it with preload data for compensation. Velocity adjustment parameters (such as the slope during the acceleration stage) are quantified into weight matrix coefficients, enabling the graph attention network to adaptively adjust the weights of entity representations in different propagation layers according to the dynamic characteristics of the actual self-alignment process. This concept achieves deep coupling between physical process parameters and deep learning models, significantly improving prediction accuracy.

[0014] Reference Figure 1 This diagram illustrates a flowchart of an embodiment of a modular assembly control method for ship cabin wall panels according to an invention. The wall panel includes vertical edge channels and horizontal edge channels; a vibration connection device operates within the vertical edge channels and horizontal edge channels; the vibration connection device includes a first magnetic field excitation array and a second magnetic field excitation array; specifically, it may include the following steps: Step 101: Obtain the length and width data of the wall panel; In this embodiment of the invention, the length data and width data include the length data and width data of the vertical edge channel and the horizontal edge channel; Furthermore, the wall panel refers to the enclosing structural unit of a ship's cabin, including vertical edge passages and horizontal edge passages, used to construct the walls, ceilings and floors of the cabin. Its surface material can be aluminum plate or steel plate, and the embodiments of the present invention do not impose too many restrictions on this.

[0015] Vertical edge channels refer to the connection structures set along the height of the wall panels, used to connect adjacent wall panels in the vertical direction.

[0016] A transverse edge channel refers to a connection structure set along the length of a wall panel, used to connect adjacent wall panels in the horizontal direction.

[0017] The vibration connection device can be a device installed within the edge channel of the wall panel. It generates high-frequency vibration through the magnetostrictive effect, driving relative displacement and heating of the connection interface to achieve a precise connection of the wall panels. Figure 2 As shown, the first magnetic field excitation array and the second magnetic field excitation array can operate in the vertical edge channel and the horizontal edge channel, connecting multiple wall panels in different directions. They achieve initial connection under high-frequency vibration and can then be further welded.

[0018] The first magnetic field excitation array can be a magnetic field excitation array set in the vertical edge channel, consisting of multiple high-frequency coils arranged at a predetermined interval, used to generate a high-frequency alternating magnetic field when energized.

[0019] The second magnetic field excitation array can be a magnetic field excitation array set in the transverse edge channel, consisting of multiple high-frequency coils arranged at a predetermined interval, used to generate a high-frequency alternating magnetic field when energized.

[0020] A magnetic field excitation array is an array structure composed of multiple high-frequency coils arranged at a predetermined interval. It is used to generate a high-frequency alternating magnetic field when energized, thereby driving magnetostrictive materials to produce high-frequency vibrations.

[0021] In this embodiment of the invention, the geometric dimensions of the wall panel to be assembled can be obtained using a laser rangefinder, scanner, or pre-recorded design drawings. The length and width data include the length and width data of the vertical and horizontal edge channels; this embodiment of the invention does not impose excessive limitations on these aspects.

[0022] Step 102: Calculate the first initial current of the first magnetic field excitation array and the second initial current of the second magnetic field excitation array based on the length data and width data; In this embodiment of the invention, calculating the first initial current of the first magnetic field excitation array and the second initial current of the second magnetic field excitation array based on the length data and width data includes: The area of ​​the joint surface is calculated based on the length and width data of the vertical and horizontal edge channels, and the power data of the magnetic field excitation array is calculated based on the area. The first initial current of the first magnetic field excitation array and the second initial current of the second magnetic field excitation array are obtained by querying the power data.

[0023] Specifically, this area can refer to the joint area, that is, the area of ​​contact between the two wall panels when they are joined together; the heating power required for the connection interface of the present invention is proportional to the joint area. The required power is determined by calculating the joint area, and then the initial current value is retrieved according to the power-current mapping relationship to provide a reference for subsequent current correction.

[0024] The area of ​​the joint surface is calculated based on the length and width data of the vertical and horizontal edge channels. The formula for calculating the area of ​​the joint surface is: S = L × W, where L is the length and W is the width.

[0025] Secondly, the power data of the magnetic field excitation array is calculated using the area. The required power calculation formula is: P = k × S, where P is the required power, S is the bonding area, and k is an empirical coefficient with a value ranging from 0.5 to 2.0 W / mm². 2 . Finally, by querying a preset current-power mapping table based on the power data, the first initial current of the first magnetic field excitation array and the second initial current of the second magnetic field excitation array are obtained. The current-power mapping table is preset and records the output power of the magnetic field excitation array under different current values.

[0026] Step 103: Collect the dielectric loss factor and vibration frequency coefficient of the wall panel material; Furthermore, the dielectric loss factor and vibration frequency coefficient of the wall panel material can also be collected. The dielectric loss factor is a physical parameter that reflects the degree of energy loss of the wall panel material under the action of a high-frequency electric field, reflecting the material's ability to absorb electromagnetic energy. The vibration frequency coefficient is an efficiency parameter of the magnetostrictive material to generate mechanical vibration under the action of an alternating magnetic field, which is related to the magnetostrictive coefficient, elastic modulus and prestress state of the material.

[0027] In this embodiment of the invention, the dielectric loss factor reflects the energy conversion efficiency of the wall panel material under a high-frequency magnetic field, while the vibration frequency coefficient is related to the resonance characteristics of the magnetostrictive material. These two parameters directly affect the effect of high-frequency tribothermal heating. Different wall panel materials have different dielectric loss factors and vibration frequency coefficients, which directly affect the efficiency of high-frequency tribothermal heating. By introducing these two parameters to correct the initial current, the excitation current is matched with the actual characteristics of the material, ensuring the stability and consistency of the heating effect.

[0028] Step 104: Correct the first initial current and the second initial current according to the dielectric loss factor and the vibration frequency coefficient to obtain the first operating current and the second operating current; In this embodiment of the invention, the step of correcting the first initial current and the second initial current according to the dielectric loss factor and the vibration frequency coefficient to obtain the first operating current and the second operating current includes: Obtain a first deviation value between the dielectric loss factor and a preset standard dielectric loss factor, and a second deviation value between the vibration frequency coefficient and a preset standard vibration frequency coefficient; When the first deviation value exceeds the first threshold, a first correction coefficient is generated based on the first deviation value; when the second deviation value exceeds the second threshold, a second correction coefficient is generated based on the second deviation value. The first initial current and the first correction coefficient are nonlinearly mapped to obtain a first intermediate current value; the second initial current and the second correction coefficient are nonlinearly mapped to obtain a second intermediate current value. The real-time temperature data of the wall panel connection interface is obtained, and the first intermediate current value and the second intermediate current value are dynamically compensated based on the real-time temperature data to generate the first operating current and the second operating current.

[0029] First, obtain the first deviation value between the dielectric loss factor and the preset standard dielectric loss factor, and the second deviation value between the vibration frequency coefficient and the preset standard vibration frequency coefficient.

[0030] Secondly, when the first deviation value exceeds the first threshold, a first correction coefficient is generated based on the first deviation value; when the second deviation value exceeds the second threshold, a second correction coefficient is generated based on the second deviation value. The first threshold and the second threshold are set according to process requirements.

[0031] Then, a nonlinear mapping operation is performed between the first initial current and the first correction coefficient to obtain a first intermediate current value; similarly, a nonlinear mapping operation is performed between the second initial current and the second correction coefficient to obtain a second intermediate current value. The nonlinear mapping operation uses the following formula: ;in, The adjusted current value. This is the initial current value. This is the dielectric loss factor deviation value. For standard dielectric loss factor, This represents the deviation value of the vibration frequency coefficient. The standard vibration frequency coefficient, , , These are the preset coupling weight coefficients.

[0032] Finally, real-time temperature data of the wall panel connection interface is obtained, and the first intermediate current value and the second intermediate current value are dynamically compensated based on the real-time temperature data to generate the first operating current and the second operating current.

[0033] In this embodiment of the invention, adaptive compensation for material differences is achieved through dual correction of the dielectric loss factor and the vibration frequency coefficient; by introducing a cross-coupling term, the nonlinear interaction between the two parameters can be captured, making the current correction model more closely resemble the actual physical process; and through real-time temperature closed-loop compensation, the temperature at the connection interface is ensured to be precisely controllable, and the temperature field uniformity is significantly better than that of traditional heating methods. Step 105: Calculate the swing distance data of the first magnetic field excitation array and the second magnetic field excitation array based on the vibration frequency coefficient; In this embodiment of the invention, calculating the swing distance data of the first magnetic field excitation array and the second magnetic field excitation array based on the vibration frequency coefficient includes: Obtain the frequency deviation value between the vibration frequency coefficient and the preset standard vibration frequency coefficient; The reference swing distance is obtained by querying a preset swing distance mapping table based on the frequency deviation value; wherein, the swing distance mapping table is used to characterize the correspondence between the vibration frequency coefficient and the expansion and contraction of the magnetostrictive material; Obtain the preload data at the wall panel connection interface, and generate a compensation coefficient based on the preload data; Multiply the reference swing distance by the compensation coefficient to obtain the swing distance data; The swing distance data is used to characterize the magnitude of the relative displacement generated at the interface of the wall panel driven by the magnetic field excitation array.

[0034] Swing distance data refers to the amplitude value that characterizes the relative displacement generated at the interface of the wall panel driven by the magnetic field excitation array.

[0035] Preload data can be the initial clamping force applied to the connection interface before vibration, obtained through a pressure sensor.

[0036] The amount of expansion (i.e., the swing distance) of a magnetostrictive material under the action of an alternating magnetic field is directly related to the vibration frequency coefficient. By calculating the swing distance, the micrometer-level relative displacement amplitude required for the self-alignment stage can be determined, providing a basis for the generation of subsequent velocity adjustment parameters.

[0037] First, the frequency deviation value between the vibration frequency coefficient and the preset standard vibration frequency coefficient is obtained.

[0038] Secondly, the reference swing distance is obtained by consulting a preset swing distance mapping table based on the frequency deviation value. This swing distance mapping table characterizes the correspondence between the vibration frequency coefficient and the expansion / contraction of the magnetostrictive material, and is obtained through experimental calibration.

[0039] Then, the preload data of the wall panel connection interface is obtained, and a compensation coefficient is generated based on the preload data. The greater the preload, the more difficult it is for the material to deform, and the smaller the actual swing distance. Therefore, a compensation coefficient needs to be introduced for correction.

[0040] Finally, the reference swing distance is multiplied by the compensation coefficient to obtain the swing distance data. This swing distance data is used to characterize the amplitude of the relative displacement generated at the interface of the wall panel driven by the magnetic field excitation array.

[0041] In a specific example of this invention, if the frequency deviation is 0.92 - 1.00 = -0.08, consulting the swing distance mapping table, the reference swing distance corresponding to the standard vibration frequency coefficient is 50 μm, and the reference swing distance corresponding to the frequency deviation of -0.08 is 38 μm. The preload data obtained from the pressure sensor is 12 kN, the standard preload is 10 kN, and the preload deviation is +20%. Based on the negative correlation between the preload deviation and the compensation coefficient, a compensation coefficient of 0.92 is generated. Therefore, the swing distance data is 38 μm × 0.92 = 34.96 μm.

[0042] By mapping the vibration frequency coefficient to the swing distance, the self-aligned displacement amplitude is quantitatively determined; by compensating for the preload, the swing distance is matched with the actual interface state, avoiding the problems of motion obstruction due to excessive preload or vibration instability due to insufficient preload.

[0043] Step 106: Generate speed adjustment parameters for the first magnetic field excitation array and the second magnetic field excitation array based on the swing distance data; Specifically, in this embodiment of the invention, the step of generating velocity adjustment parameters for the first magnetic field excitation array and the second magnetic field excitation array based on the swing distance data includes: Calculate the required acceleration curve based on the swing distance data; Obtain the elastic modulus of the wall panel material and the contact stiffness of the connection interface, and calculate the maximum allowable acceleration based on the elastic modulus, contact stiffness and swing distance data; The acceleration curve is limited based on the maximum permissible acceleration to obtain the limited acceleration curve. The speed adjustment parameters are extracted from the acceleration curve after the amplitude limiting process.

[0044] In this embodiment of the invention, the speed adjustment parameters may include the acceleration phase slope, the constant speed phase holding time, and the deceleration phase slope, which are used to control the motion characteristics during the self-alignment phase.

[0045] The elastic modulus is the ratio of stress to strain in a material during the elastic deformation stage, reflecting the material's ability to resist elastic deformation.

[0046] Contact stiffness is the ability of a connection interface to resist deformation under normal load.

[0047] During self-alignment, the relative motion of the panel interfaces needs to be smooth and controllable to avoid interface impact damage caused by sudden velocity changes. By generating velocity adjustment parameters, the rate of change of acceleration during the motion can be controlled, achieving smooth start and stop.

[0048] In one specific example, firstly, the required acceleration curve is calculated based on the swing distance data. The acceleration curve includes an acceleration phase, a constant velocity phase, and a deceleration phase, and is designed with an S-curve to make the motion smooth.

[0049] Secondly, the elastic modulus of the wall panel material and the contact stiffness of the connection interface are obtained. Based on the elastic modulus, contact stiffness, and swing distance data, the maximum allowable acceleration is calculated. The calculation of the maximum allowable acceleration is based on ensuring that the interface contact stress does not exceed the yield strength of the material.

[0050] Then, the acceleration curve is subjected to amplitude limiting processing based on the maximum permissible acceleration to obtain the amplitude-limited acceleration curve.

[0051] Finally, speed adjustment parameters are generated based on the acceleration curve after amplitude limiting. These speed adjustment parameters include the slope of the acceleration phase, the holding time of the constant speed phase, and the slope of the deceleration phase. This embodiment of the invention does not impose too many restrictions on these parameters.

[0052] In this embodiment of the invention, by limiting the maximum permissible acceleration, the acceleration during the self-alignment process is ensured not to exceed the material's bearing capacity, thus avoiding interface impact damage; by designing an S-shaped acceleration curve, smooth start and stop of motion is achieved, improving alignment accuracy; and by quantitatively generating speed adjustment parameters, the self-alignment process becomes predictable and controllable.

[0053] Step 107: Control the operation of the first magnetic field excitation array and the second magnetic field excitation array according to the first operating current, the second operating current, and the speed adjustment parameters.

[0054] Based on the first and second operating currents, high-frequency currents with corresponding power are output to the first and second magnetic field excitation arrays, generating a high-frequency alternating magnetic field with a frequency of 30kHz-50kHz. The magnetostrictive material generates high-frequency stretching vibrations under the action of the high-frequency magnetic field, driving the wall panel interface to produce relative displacement according to the motion curve set by the speed adjustment parameters. Interface connection is achieved through high-frequency frictional heating. By inputting the corrected operating current and speed adjustment parameters into the magnetic field excitation array, precise control of the high-frequency alternating magnetic field is achieved, thereby driving the wall panel interface to generate controllable high-frequency frictional heating and self-aligning motion, completing modular assembly. Through precise current and speed control, coordinated control of high-frequency frictional heating and self-aligning motion is achieved; utilizing the uniform temperature field characteristics of magnetostrictive high-frequency frictional heating solves the problem of uneven temperature distribution in traditional heating methods.

[0055] In a preferred example, the method further includes: Obtain the operating results of the first magnetic field excitation array and the second magnetic field excitation array; Extract the entities, relationships, and attributes of the operating results, first operating current, second operating current, and speed adjustment parameters to form an entity set and a relationship set; The entity set and relation set are input into the collaborative message layer to obtain the runtime assembly information; The runtime assembly information is input into the feature learning layer to generate the runtime assembly topology. The prediction layer is calculated for the aforementioned operational assembly topology, and the entities of different collaborative message layers are weighted to obtain the trained prediction model. The new first operating current, second operating current, and speed adjustment parameters are input into the prediction model to obtain the output operating results.

[0056] In this embodiment of the invention, structured data is first converted into an entity-relationship-attribute format of a knowledge graph. Entities (such as "operating current parameter", "velocity parameter", "temperature field", "connection strength"), relations (such as "increased operating current parameter leads to increased control frequency"), and attributes (such as the specific value of the control frequency) are extracted from the data. The extraction results are stored in the form of triples. A triple is generated, such as (velocity parameter 0.5 m / s). 3 , association, connection strength 180MPa), etc., to form a set of entities and a set of relationships.

[0057] Furthermore, the collaborative message layer is used to propagate collaborative information between entities along the edge of the knowledge graph. Through multi-hop propagation, it captures higher-order associations, enabling the model to learn deep dependencies between process parameters. Employing a graph neural network message propagation mechanism, starting from an initial entity set, it performs multi-hop propagation along the links of the knowledge graph to obtain higher-order entity sets of operating parameters and results. In this embodiment of the invention, multi-hop message propagation captures higher-order associations between process parameters, enabling the model to learn deeper causal relationships and improving prediction accuracy.

[0058] In this embodiment of the invention, the feature learning layer employs a graph attention feature learning network. By learning the topological proximity features between entities, it generates high-order semantic information to meet the requirements of fine-grained representation. The graph attention mechanism calculates the attention weights of different tail entities, aggregates domain entity information to generate target-oriented domain information, and obtains high-order semantic information by stacking network layers. For example, for the "current parameter" node, the attention network calculates its attention weights with neighboring nodes such as "temperature field," "stress field," and "vibration parameter," and after weighted aggregation, generates a node representation containing high-order semantics. Through the graph attention mechanism, the model can automatically distinguish the importance of different neighboring nodes, generating more refined entity embedding representations and improving the accuracy of feature expression.

[0059] Furthermore, the prediction layer in this embodiment of the invention can employ an attention aggregator to assign attention weights to entities in different propagation layers, generating refined entity embedding representations, and finally predicting connection quality results based on these entity embedding representations. By assigning weights to entities in different propagation layers through the attention aggregator, the model can distinguish the importance of information at different levels, generating more accurate prediction results; and by incorporating the velocity adjustment parameter into the weight matrix, deep coupling between process parameters and the prediction model is achieved.

[0060] In a preferred example, the operation of the prediction layer on the running assembly topology, which involves weighting entities from different collaborative message layers to obtain the trained prediction model, includes: Generate the acceleration coefficient corresponding to the speed adjustment parameters; Based on the acceleration coefficients, the weight matrix coefficients are determined, and a new weight matrix is ​​obtained; The prediction layer is calculated using a new weight matrix on the assembled topology, and entities in different collaborative message layers are weighted to obtain the trained prediction model.

[0061] First, the acceleration phase slope is extracted from the speed adjustment parameters and denoted as... .

[0062] Secondly, obtain the preset standard acceleration phase slope, denoted as... The slope of the preset standard acceleration phase can be obtained through statistical analysis of historical optimal process parameters.

[0063] Then, calculate the acceleration coefficient according to the following formula. : ;in, The smoothing factor, ranging from 0.8 to 1.2, can be fine-tuned according to actual working conditions. By quantifying the speed adjustment parameter into an acceleration coefficient, a numerical characterization of the dynamic characteristics of the self-alignment process is achieved, providing a basis for subsequent weight matrix adjustment.

[0064] The step of determining the weight matrix coefficients based on the acceleration coefficients to obtain a new weight matrix specifically includes: First, obtain the original set of coefficients for the baseline weight matrix. ,in This represents the total number of collaborative message layers. Indicates the first The baseline weight of the layer.

[0065] Secondly, according to the acceleration coefficient Calculate the adjustment factor for each layer : ; in, The average number of floors. The meaning of this formula is: when the acceleration coefficient is large (slow motion), the weight of deep propagation increases relatively; when the acceleration coefficient is small (rapid motion), the weight of shallow propagation increases relatively.

[0066] Then, calculate the coefficients of the new weight matrix. : ;in, This represents the adjustment factor for the j-th layer; Finally, the coefficients of the new weight matrix are combined to form a new weight matrix. .

[0067] In this embodiment of the invention, by dynamically adjusting the weight matrix coefficients through acceleration coefficients, the model can adaptively adjust the weights of entity representations at each layer according to the dynamic characteristics of the actual self-alignment process. When the motion is smooth, more attention is paid to the higher-order operational information of deep propagation, and when the motion is rapid, more attention is paid to the direct correlation information of shallow propagation, thereby improving the adaptability and accuracy of the prediction model.

[0068] Furthermore, the entity embeddings of each collaborative message layer output are obtained, and a new weight matrix is ​​used. The entity embeddings of each layer are weighted and aggregated to obtain the final entity embedding representation. The final entity embedding representation is then input into the prediction layer. The prediction result is calculated using the output layer weight matrix and activation function. The model parameters are updated using the backpropagation algorithm to minimize the loss function between the prediction result and the actual running result, thus obtaining the trained prediction model.

[0069] In this embodiment of the invention, a trained prediction model is used to predict the operating results under new operating conditions, thereby optimizing process parameters and predicting quality.

[0070] The new process parameters are input into the trained prediction model, and the model calculates the results through forward propagation.

[0071] In one specific example, for a new wall panel module (2800mm in length and 60mm in width), with the input of the corrected operating current of 312A and speed adjustment parameters, the model predicts a connection strength of 192MPa and a temperature field temperature difference of 4.2℃, which meets the process requirements and allows assembly to be performed.

[0072] Predictive models enable pre-assessment of connection quality, avoiding trial-and-error costs; by continuously accumulating operational data, the model can be continuously optimized, enabling the continuous accumulation and iteration of process knowledge.

[0073] In this embodiment of the invention, the modular assembly control method for the wall panels of a ship's cabin includes: acquiring length and width data of the wall panels; calculating a first initial current of a first magnetic field excitation array and a second initial current of a second magnetic field excitation array based on the length and width data; collecting the dielectric loss factor and vibration frequency coefficient of the wall panel material; correcting the first and second initial currents based on the dielectric loss factor and vibration frequency coefficient to obtain a first operating current and a second operating current; calculating the swing distance data of the first and second magnetic field excitation arrays based on the vibration frequency coefficient; generating speed adjustment parameters for the first and second magnetic field excitation arrays based on the swing distance data; controlling the operation of the first and second magnetic field excitation arrays based on the first and second operating currents and the speed adjustment parameters, wherein the magnetostrictive material generates high-frequency stretching vibration under the action of a high-frequency magnetic field, driving the wall panel interface to generate relative displacement according to the motion curve set by the speed adjustment parameters, and achieving interface connection through high-frequency frictional heating. By inputting the corrected operating current and speed adjustment parameters into the magnetic field excitation array, precise control of the high-frequency alternating magnetic field is achieved, thereby driving the wall panel interface to generate controllable high-frequency frictional heating and self-aligning motion, completing the modular assembly. Through precise current and speed control, the coordinated control of high-frequency frictional heating and self-aligned motion is achieved; by utilizing the uniform temperature field characteristics of magnetostrictive high-frequency frictional heating, the problem of uneven temperature distribution in traditional heating methods is solved.

[0074] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0075] Reference Figure 3 This diagram illustrates a structural block diagram of an embodiment of a modular assembly control system for ship cabin walls according to an embodiment of the present invention. The wall panel includes a vertical edge channel and a horizontal edge channel; the vibration connection device operates in the vertical edge channel and the horizontal edge channel; the vibration connection device includes a first magnetic field excitation array and a second magnetic field excitation array; specifically, it may include the following modules: The first acquisition module 301 is used to acquire the length and width data of the wall panel; The initial current calculation module 302 is used to calculate the first initial current of the first magnetic field excitation array and the second initial current of the second magnetic field excitation array based on the length data and width data. The acquisition module 303 is used to acquire the dielectric loss factor and vibration frequency coefficient of the wall panel material; The current correction module 304 is used to correct the first initial current and the second initial current according to the dielectric loss factor and the vibration frequency coefficient to obtain the first operating current and the second operating current. The swing distance calculation module 305 is used to calculate the swing distance data of the first magnetic field excitation array and the second magnetic field excitation array based on the vibration frequency coefficient. The speed adjustment parameter generation module 306 is used to generate speed adjustment parameters for the first magnetic field excitation array and the second magnetic field excitation array based on the swing distance data. The operation control module 307 is used to control the operation of the first magnetic field excitation array and the second magnetic field excitation array according to the first operating current, the second operating current, and the speed adjustment parameters.

[0076] Preferably, the system further includes: The operation result acquisition module is used to acquire the operation results of the first magnetic field excitation array and the second magnetic field excitation array; The knowledge graph construction module is used to extract the entities, relationships, and attributes of the running results, the first running current, the second running current, and the speed adjustment parameters, forming an entity set and a relationship set; The collaborative message propagation module is used to input the entity set and relationship set into the collaborative message layer to obtain runtime assembly information; The feature learning module is used to input the runtime assembly information into the feature learning layer to generate the runtime assembly topology. The prediction model training module is used to perform prediction layer operations on the running assembly topology, assign weights to entities in different collaborative message layers, and obtain the trained prediction model. The result prediction module is used to input the new first operating current, second operating current, and speed adjustment parameters into the prediction model to obtain the output operating results.

[0077] Preferably, the initial current calculation module includes: The joint area calculation submodule is used to calculate the area of ​​the joint surface based on the length and width data of the vertical edge channel and the horizontal edge channel; A power calculation submodule is used to calculate the power data of the magnetic field excitation array based on the area. The current query submodule is used to query the first initial current of the first magnetic field excitation array and the second initial current of the second magnetic field excitation array based on the power data.

[0078] Preferably, the current correction module includes: The deviation value acquisition submodule is used to acquire a first deviation value between the dielectric loss factor and the preset standard dielectric loss factor, and a second deviation value between the vibration frequency coefficient and the preset standard vibration frequency coefficient. The correction coefficient generation submodule is used to generate a first correction coefficient based on the first deviation value when the first deviation value exceeds a first threshold, and to generate a second correction coefficient based on the second deviation value when the second deviation value exceeds a second threshold. The nonlinear mapping submodule is used to perform a nonlinear mapping operation between the first initial current and the first correction coefficient to obtain a first intermediate current value; and to perform a nonlinear mapping operation between the second initial current and the second correction coefficient to obtain a second intermediate current value. The temperature compensation submodule is used to acquire real-time temperature data of the wall panel connection interface, and dynamically compensate the first intermediate current value and the second intermediate current value according to the real-time temperature data to generate the first operating current and the second operating current.

[0079] Preferably, the swing distance calculation module includes: The frequency deviation acquisition submodule is used to acquire the frequency deviation value between the vibration frequency coefficient and the preset standard vibration frequency coefficient; The reference swing distance query submodule is used to query a preset swing distance mapping table based on the frequency deviation value to obtain the reference swing distance; wherein, the swing distance mapping table is used to characterize the correspondence between the vibration frequency coefficient and the expansion and contraction of the magnetostrictive material; The compensation coefficient generation submodule is used to obtain the preload data of the wall panel connection interface and generate the compensation coefficient based on the preload data. The swing distance calculation submodule is used to multiply the reference swing distance by the compensation coefficient to obtain swing distance data; wherein, the swing distance data is used to characterize the amplitude of the relative displacement generated by the magnetic field excitation array driving the wall panel interface.

[0080] Preferably, the speed adjustment parameter generation module includes: An acceleration curve calculation submodule is used to calculate the required acceleration curve based on the swing distance data. The maximum allowable acceleration calculation submodule is used to obtain the elastic modulus of the wall panel material and the contact stiffness of the connection interface, and calculate the maximum allowable acceleration based on the elastic modulus, contact stiffness and swing distance data; A limiting processing submodule is used to limit the acceleration curve according to the maximum allowable acceleration to obtain a limited acceleration curve. The velocity parameter extraction submodule is used to generate velocity adjustment parameters based on the acceleration curve after amplitude limiting.

[0081] Preferably, the prediction model training module includes: An acceleration coefficient generation submodule is used to generate the acceleration coefficient corresponding to the speed adjustment parameters; The weight matrix coefficient determination submodule is used to determine the weight matrix coefficients based on the acceleration coefficients to obtain a new weight matrix. The weight allocation submodule is used to perform prediction layer operations on the running assembly topology using a new weight matrix, and to allocate weights to entities in different collaborative message layers to obtain the trained prediction model.

[0082] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0083] Specific limitations regarding the modular assembly control system for ship cabin panels can be found in the above-mentioned limitations on the modular assembly control method for ship cabin panels, and will not be repeated here. Each module in the aforementioned modular assembly control system for ship cabin panels can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0084] The modular assembly control system for ship cabin walls provided above can be used to execute the modular assembly control method for ship cabin walls provided in any of the above embodiments, and has corresponding functions and beneficial effects.

[0085] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for modular assembly control of ship cabin wall panels. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device casing, or an external keyboard, touchpad, or mouse.

[0086] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0087] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the steps described above.

[0088] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, performs the steps described above.

[0089] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0090] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0091] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0092] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of apparatus, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0093] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction methods implemented in a process. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0094] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0095] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0096] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, apparatus, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or terminal device that includes said element.

[0097] The present invention has provided a detailed description of a modular assembly control method for ship cabin wall panels, a modular assembly control system for ship cabin wall panels, a computer device, and a storage medium. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for controlling the modular assembly of wall panels in a ship's cabin, characterized in that, The wall panel includes vertical edge channels and horizontal edge channels; a vibration connection device operates within the vertical edge channels and horizontal edge channels; the vibration connection device includes a first magnetic field excitation array and a second magnetic field excitation array; the method includes: Obtain the length and width data of the wall panel; the length and width data include the length and width data of the vertical edge channel and the horizontal edge channel; The area of ​​the joint surface is calculated based on the length and width data of the vertical and horizontal edge channels, and the power data of the magnetic field excitation array is calculated based on the area. The first initial current of the first magnetic field excitation array and the second initial current of the second magnetic field excitation array are obtained by querying the power data. Collect the dielectric loss factor and vibration frequency coefficient of the wall panel material; Obtain a first deviation value between the dielectric loss factor and a preset standard dielectric loss factor, and a second deviation value between the vibration frequency coefficient and a preset standard vibration frequency coefficient; When the first deviation value exceeds the first threshold, a first correction coefficient is generated based on the first deviation value; when the second deviation value exceeds the second threshold, a second correction coefficient is generated based on the second deviation value. The first initial current and the first correction coefficient are nonlinearly mapped to obtain a first intermediate current value; the second initial current and the second correction coefficient are nonlinearly mapped to obtain a second intermediate current value. The real-time temperature data of the wall panel connection interface is obtained, and the first intermediate current value and the second intermediate current value are dynamically compensated according to the real-time temperature data to generate the first operating current and the second operating current. The swing distance data of the first magnetic field excitation array and the second magnetic field excitation array are calculated based on the vibration frequency coefficient. Based on the swing distance data, velocity adjustment parameters for the first and second magnetic field excitation arrays are generated; The operation of the first magnetic field excitation array and the second magnetic field excitation array is controlled according to the first operating current, the second operating current, and the speed adjustment parameters. The method further includes: Obtain the operating results of the first magnetic field excitation array and the second magnetic field excitation array; Extract the entities, relationships, and attributes of the operating results, first operating current, second operating current, and speed adjustment parameters to form an entity set and a relationship set; The entity set and relation set are input into the collaborative message layer to obtain the runtime assembly information; The runtime assembly information is input into the feature learning layer to generate the runtime assembly topology. The prediction layer is calculated for the aforementioned operational assembly topology, and the entities of different collaborative message layers are weighted to obtain the trained prediction model. The new first operating current, second operating current, and speed adjustment parameters are input into the prediction model to obtain the output operating results.

2. The method according to claim 1, characterized in that, The calculation of the swing distance data of the first magnetic field excitation array and the second magnetic field excitation array based on the vibration frequency coefficient includes: Obtain the frequency deviation value between the vibration frequency coefficient and the preset standard vibration frequency coefficient; The reference swing distance is obtained by querying a preset swing distance mapping table based on the frequency deviation value; wherein, the swing distance mapping table is used to characterize the correspondence between the vibration frequency coefficient and the expansion and contraction of the magnetostrictive material; Obtain the preload data at the wall panel connection interface, and generate a compensation coefficient based on the preload data; Multiply the reference swing distance by the compensation coefficient to obtain the swing distance data; The swing distance data is used to characterize the magnitude of the relative displacement generated at the interface of the wall panel driven by the magnetic field excitation array.

3. The method according to claim 1, characterized in that, The generation of velocity adjustment parameters for the first and second magnetic field excitation arrays based on the swing distance data includes: Calculate the required acceleration curve based on the swing distance data; Obtain the elastic modulus of the wall panel material and the contact stiffness of the connection interface, and calculate the maximum allowable acceleration based on the elastic modulus, contact stiffness and swing distance data; The acceleration curve is limited based on the maximum permissible acceleration to obtain the limited acceleration curve. The speed adjustment parameters are extracted from the acceleration curve after the amplitude limiting process.

4. The method according to claim 3, characterized in that, The calculation of the prediction layer for the running assembly topology, which assigns weights to entities in different collaborative message layers to obtain the trained prediction model, includes: Generate the acceleration coefficient corresponding to the speed adjustment parameters; Based on the acceleration coefficients, the weight matrix coefficients are determined, and a new weight matrix is ​​obtained; The prediction layer is calculated using a new weight matrix on the assembled topology, and entities in different collaborative message layers are weighted to obtain the trained prediction model.

5. A modular assembly control system for ship cabin wall panels, characterized in that, The wall panel includes vertical edge channels and horizontal edge channels; a vibration connection device operates within the vertical edge channels and horizontal edge channels; the vibration connection device includes a first magnetic field excitation array and a second magnetic field excitation array; the system includes: The first acquisition module is used to acquire the length data and width data of the wall panel; the length data and width data include the length data and width data of the vertical edge channel and the horizontal edge channel; The initial current calculation module is used to calculate the area of ​​the joint surface based on the length and width data of the vertical edge channel and the horizontal edge channel, and to calculate the power data of the magnetic field excitation array through the area. The first initial current of the first magnetic field excitation array and the second initial current of the second magnetic field excitation array are obtained by querying the power data. The acquisition module is used to collect the dielectric loss factor and vibration frequency coefficient of the wall panel material; The current correction module is used to obtain a first deviation value between the dielectric loss factor and the preset standard dielectric loss factor, and a second deviation value between the vibration frequency coefficient and the preset standard vibration frequency coefficient. When the first deviation value exceeds the first threshold, a first correction coefficient is generated based on the first deviation value; when the second deviation value exceeds the second threshold, a second correction coefficient is generated based on the second deviation value. The first initial current and the first correction coefficient are nonlinearly mapped to obtain a first intermediate current value; the second initial current and the second correction coefficient are nonlinearly mapped to obtain a second intermediate current value. The real-time temperature data of the wall panel connection interface is obtained, and the first intermediate current value and the second intermediate current value are dynamically compensated according to the real-time temperature data to generate the first operating current and the second operating current. The swing distance calculation module is used to calculate the swing distance data of the first magnetic field excitation array and the second magnetic field excitation array based on the vibration frequency coefficient. The speed adjustment parameter generation module is used to generate speed adjustment parameters for the first magnetic field excitation array and the second magnetic field excitation array based on the swing distance data. The operation control module is used to control the operation of the first magnetic field excitation array and the second magnetic field excitation array according to the first operating current, the second operating current, and the speed adjustment parameters; The system also includes: Obtain the operating results of the first magnetic field excitation array and the second magnetic field excitation array; Extract the entities, relationships, and attributes of the operating results, first operating current, second operating current, and speed adjustment parameters to form an entity set and a relationship set; The entity set and relation set are input into the collaborative message layer to obtain the runtime assembly information; The runtime assembly information is input into the feature learning layer to generate the runtime assembly topology. The prediction layer is calculated for the aforementioned operational assembly topology, and the entities of different collaborative message layers are weighted to obtain the trained prediction model. The new first operating current, second operating current, and speed adjustment parameters are input into the prediction model to obtain the output operating results.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the modular assembly control method for the wall panels of a ship compartment as described in any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the modular assembly control method for the wall panels of the ship compartment as described in any one of claims 1 to 4.

Images